mirror of
https://github.com/lancedb/lancedb.git
synced 2026-05-31 19:00:39 +00:00
Compare commits
6 Commits
codex/upda
...
v0.30.0
| Author | SHA1 | Date | |
|---|---|---|---|
|
a5288de8d1 | ||
|
|
7a41f4a5eb | ||
|
|
28fc8f0f26 | ||
|
|
7677a5279c | ||
|
b6c645592a | ||
|
|
a9f49c8150 |
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.30.0-beta.1"
|
||||
current_version = "0.30.0"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
133
Cargo.lock
generated
133
Cargo.lock
generated
@@ -976,15 +976,16 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "aws-smithy-runtime"
|
||||
version = "1.11.1"
|
||||
version = "1.11.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0504b1ab12debb5959e5165ee5fe97dd387e7aa7ea6a477bfd7635dfe769a4f5"
|
||||
checksum = "b8e6f5caf6fea86f8c2206541ab5857cfcda9013426cdbe8fa0098b9e2d32182"
|
||||
dependencies = [
|
||||
"aws-smithy-async",
|
||||
"aws-smithy-http",
|
||||
"aws-smithy-http-client",
|
||||
"aws-smithy-observability",
|
||||
"aws-smithy-runtime-api",
|
||||
"aws-smithy-schema",
|
||||
"aws-smithy-types",
|
||||
"bytes",
|
||||
"fastrand",
|
||||
@@ -1001,9 +1002,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "aws-smithy-runtime-api"
|
||||
version = "1.12.0"
|
||||
version = "1.12.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b71a13df6ada0aafbf21a73bdfcdf9324cfa9df77d96b8446045be3cde61b42e"
|
||||
checksum = "dc117c179ecf39a62a0a3f49f600e9ac26a7ad7dd172177999f83933af776c32"
|
||||
dependencies = [
|
||||
"aws-smithy-async",
|
||||
"aws-smithy-runtime-api-macros",
|
||||
@@ -1029,10 +1030,21 @@ dependencies = [
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "aws-smithy-types"
|
||||
version = "1.4.7"
|
||||
name = "aws-smithy-schema"
|
||||
version = "0.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9d73dbfbaa8e4bc57b9045137680b958d274823509a360abfd8e1d514d40c95c"
|
||||
checksum = "7442cb268338f0eb8278140a107c046756aa01093d8ef5e99628d34ae09c94f5"
|
||||
dependencies = [
|
||||
"aws-smithy-runtime-api",
|
||||
"aws-smithy-types",
|
||||
"http 1.4.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "aws-smithy-types"
|
||||
version = "1.4.8"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "056b66dbce2f81cc0c1e2b05bb402eb58f8a3530479d650efadd5bbae9a4050b"
|
||||
dependencies = [
|
||||
"base64-simd",
|
||||
"bytes",
|
||||
@@ -3284,8 +3296,9 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
|
||||
|
||||
[[package]]
|
||||
name = "fsst"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bcd0ce0249ac12fd44fcde62d435c36d881952c2f0df4d1de24b45e1dbba5ddb"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"rand 0.9.4",
|
||||
@@ -4506,8 +4519,9 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
|
||||
|
||||
[[package]]
|
||||
name = "lance"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3944aca86f4c78f4da04af1c2bf33e664a2826b7af72972ad200d6b9de59019f"
|
||||
dependencies = [
|
||||
"arc-swap",
|
||||
"arrow",
|
||||
@@ -4552,7 +4566,6 @@ dependencies = [
|
||||
"lance-io",
|
||||
"lance-linalg",
|
||||
"lance-namespace",
|
||||
"lance-select",
|
||||
"lance-table",
|
||||
"lance-tokenizer",
|
||||
"log",
|
||||
@@ -4580,8 +4593,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-arrow"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "253f4a0a70580c985b91e65e9ca6cad644825a4078de28d8efbacf3ffbd7ecdc"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4601,8 +4615,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-bitpacking"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "80c4d12521b1945041dd515a56aa0854973138e7ac12111c92572e33e4ecb593"
|
||||
dependencies = [
|
||||
"arrayref",
|
||||
"paste",
|
||||
@@ -4611,8 +4626,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-core"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "13f84020da5a484e2f07dd1796e09785ed7cd889857ebc4cb77e32ef214ee594"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4647,8 +4663,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datafusion"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7460597a66534a75987993d4dac5bc330586d99c5b79ae73367dbcbd4e29e576"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4678,8 +4695,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datagen"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "046f5506ed2271cd941a050de7bf535dd3aedc291aadec836a63fa56c5926e3b"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4697,8 +4715,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-encoding"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7af54edf43dcf9d6a56cc636eb35d457e68373c6448dca3f0891b3325b4a24e6"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -4733,8 +4752,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-file"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0772ae2d6207995dc1eb28aff9507f78e90b3362b58f311da001e9dc25f3d736"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -4765,8 +4785,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-index"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e71fbfb51096a903cb524fe0da716f5f15fbc4a6b6f84cd6dec21abf319c5e84"
|
||||
dependencies = [
|
||||
"arc-swap",
|
||||
"arrow",
|
||||
@@ -4803,7 +4824,6 @@ dependencies = [
|
||||
"lance-file",
|
||||
"lance-io",
|
||||
"lance-linalg",
|
||||
"lance-select",
|
||||
"lance-table",
|
||||
"lance-tokenizer",
|
||||
"libm",
|
||||
@@ -4831,8 +4851,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-io"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bab8c98ef1b870b20541d27f3ca4efdf7c9f5c25214233be07d231ba88900219"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-arith",
|
||||
@@ -4874,8 +4895,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-linalg"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6b4c51cad0ac780b02dc4da48528479e7693c03e8d05390510bbc69ca2a9a1f1"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4891,8 +4913,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "014e8332ca0615506342e0d3af608639864b68396973be14239f09c9f21f1fc2"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"async-trait",
|
||||
@@ -4904,8 +4927,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace-impls"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e8d1231906a3cf92dd3dcda7d14a09c4835af6cd2bcd76dfd2481e87f20a282d"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-ipc",
|
||||
@@ -4952,25 +4976,11 @@ dependencies = [
|
||||
"url",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lance-select"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
"byteorder",
|
||||
"bytes",
|
||||
"deepsize",
|
||||
"itertools 0.13.0",
|
||||
"lance-core",
|
||||
"roaring",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lance-table"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b16f1355904aea4ebb04ffc70c58c97901e10bde44452b4b021de4a1f329250d"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4989,7 +4999,6 @@ dependencies = [
|
||||
"lance-core",
|
||||
"lance-file",
|
||||
"lance-io",
|
||||
"lance-select",
|
||||
"log",
|
||||
"object_store",
|
||||
"prost",
|
||||
@@ -5010,8 +5019,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-testing"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3094c2aacbd1fa093d809fc54fa911e3498671ba451041341d7caaa18460e6b2"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-schema",
|
||||
@@ -5022,8 +5032,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-tokenizer"
|
||||
version = "7.1.0-beta.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9"
|
||||
version = "7.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b39b7f5ed9d0c0b716bf599b559d888267ed1dfe4c4e29d3648b51d2a28940cf"
|
||||
dependencies = [
|
||||
"jieba-rs",
|
||||
"lindera",
|
||||
@@ -8321,9 +8332,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "serde_json"
|
||||
version = "1.0.149"
|
||||
version = "1.0.150"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
|
||||
checksum = "e8014e44b4736ed0538adeecded0fce2a272f22dc9578a7eb6b2d9993c74cfb9"
|
||||
dependencies = [
|
||||
"itoa",
|
||||
"memchr",
|
||||
|
||||
28
Cargo.toml
28
Cargo.toml
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
|
||||
rust-version = "1.91.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=7.1.0-beta.4", default-features = false, "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=7.1.0-beta.4", default-features = false, "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=7.1.0-beta.4", default-features = false, "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance = { "version" = "=7.0.0", default-features = false }
|
||||
lance-core = "=7.0.0"
|
||||
lance-datagen = "=7.0.0"
|
||||
lance-file = "=7.0.0"
|
||||
lance-io = { "version" = "=7.0.0", default-features = false }
|
||||
lance-index = "=7.0.0"
|
||||
lance-linalg = "=7.0.0"
|
||||
lance-namespace = "=7.0.0"
|
||||
lance-namespace-impls = { "version" = "=7.0.0", default-features = false }
|
||||
lance-table = "=7.0.0"
|
||||
lance-testing = "=7.0.0"
|
||||
lance-datafusion = "=7.0.0"
|
||||
lance-encoding = "=7.0.0"
|
||||
lance-arrow = "=7.0.0"
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "58.0.0", optional = false }
|
||||
|
||||
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
|
||||
<dependency>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-core</artifactId>
|
||||
<version>0.30.0-beta.1</version>
|
||||
<version>0.30.0</version>
|
||||
</dependency>
|
||||
```
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
<parent>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.30.0-beta.1</version>
|
||||
<version>0.30.0-final.0</version>
|
||||
<relativePath>../pom.xml</relativePath>
|
||||
</parent>
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.30.0-beta.1</version>
|
||||
<version>0.30.0-final.0</version>
|
||||
<packaging>pom</packaging>
|
||||
<name>${project.artifactId}</name>
|
||||
<description>LanceDB Java SDK Parent POM</description>
|
||||
@@ -28,7 +28,7 @@
|
||||
<properties>
|
||||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
|
||||
<arrow.version>15.0.0</arrow.version>
|
||||
<lance-core.version>7.1.0-beta.4</lance-core.version>
|
||||
<lance-core.version>7.0.0</lance-core.version>
|
||||
<spotless.skip>false</spotless.skip>
|
||||
<spotless.version>2.30.0</spotless.version>
|
||||
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "lancedb-nodejs"
|
||||
edition.workspace = true
|
||||
version = "0.30.0-beta.1"
|
||||
version = "0.30.0"
|
||||
publish = false
|
||||
license.workspace = true
|
||||
description.workspace = true
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-arm64",
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.darwin-arm64.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-gnu",
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-musl",
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-gnu",
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-musl",
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-arm64-msvc",
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"os": [
|
||||
"win32"
|
||||
],
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-x64-msvc",
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"os": ["win32"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.win32-x64-msvc.node",
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
"ann"
|
||||
],
|
||||
"private": false,
|
||||
"version": "0.30.0-beta.1",
|
||||
"version": "0.30.0",
|
||||
"main": "dist/index.js",
|
||||
"exports": {
|
||||
".": "./dist/index.js",
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.33.0-beta.1"
|
||||
current_version = "0.33.0"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb-python"
|
||||
version = "0.33.0-beta.1"
|
||||
version = "0.33.0"
|
||||
publish = false
|
||||
edition.workspace = true
|
||||
description = "Python bindings for LanceDB"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb"
|
||||
version = "0.30.0-beta.1"
|
||||
version = "0.30.0"
|
||||
edition.workspace = true
|
||||
description = "LanceDB: A serverless, low-latency vector database for AI applications"
|
||||
license.workspace = true
|
||||
|
||||
@@ -982,4 +982,105 @@ mod tests {
|
||||
table2.add(struct_batch).execute().await.unwrap();
|
||||
assert_eq!(table2.count_rows(None).await.unwrap(), 2);
|
||||
}
|
||||
|
||||
/// Regression test: appending `arrow.json` (PyArrow `pa.json_()`) data into a table
|
||||
/// whose schema was created with `pa.json_()` (internally stored as `lance.json`, backed
|
||||
/// by `LargeBinary`) must succeed without a schema-mismatch error.
|
||||
///
|
||||
/// Previously `build_field_exprs` would attempt a `Utf8 → LargeBinary` DataFusion cast,
|
||||
/// which produced a field whose Arrow extension metadata still read `arrow.json` instead
|
||||
/// of `lance.json`. Lance-core then rejected the append with
|
||||
/// `"json vs large_binary" schema mismatch`.
|
||||
///
|
||||
/// PyArrow's `pa.json_()` may be backed by either `Utf8` or `LargeUtf8` depending on the
|
||||
/// constructor used, so the test is parameterized over the input backing type.
|
||||
#[rstest::rstest]
|
||||
#[case::utf8(DataType::Utf8)]
|
||||
#[case::large_utf8(DataType::LargeUtf8)]
|
||||
#[tokio::test]
|
||||
async fn test_add_arrow_json_into_lance_json_table(#[case] input_type: DataType) {
|
||||
use arrow_array::{Array, cast::AsArray};
|
||||
use lance_arrow::ARROW_EXT_NAME_KEY;
|
||||
use lance_arrow::json::{ARROW_JSON_EXT_NAME, JSON_EXT_NAME};
|
||||
|
||||
// Build a table whose "data" column is lance.json (LargeBinary +
|
||||
// ARROW:extension:name = "lance.json").
|
||||
let lance_json_field = lance_arrow::json::json_field("data", true);
|
||||
let table_schema = Arc::new(Schema::new(vec![lance_json_field]));
|
||||
|
||||
let db = connect("memory://").execute().await.unwrap();
|
||||
let table = db
|
||||
.create_empty_table("json_test", table_schema)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Sanity-check the stored schema.
|
||||
let stored_field = table.schema().await.unwrap();
|
||||
let data_field = stored_field.field_with_name("data").unwrap();
|
||||
assert_eq!(data_field.data_type(), &DataType::LargeBinary);
|
||||
assert_eq!(
|
||||
data_field
|
||||
.metadata()
|
||||
.get(ARROW_EXT_NAME_KEY)
|
||||
.map(|s| s.as_str()),
|
||||
Some(JSON_EXT_NAME),
|
||||
);
|
||||
|
||||
// Build an arrow.json input field (Utf8/LargeUtf8 + arrow.json extension).
|
||||
// This is what PyArrow produces for pa.json_() arrays.
|
||||
let arrow_json_metadata = std::collections::HashMap::from([(
|
||||
ARROW_EXT_NAME_KEY.to_string(),
|
||||
ARROW_JSON_EXT_NAME.to_string(),
|
||||
)]);
|
||||
let arrow_json_field =
|
||||
Field::new("data", input_type.clone(), true).with_metadata(arrow_json_metadata);
|
||||
let arrow_json_schema = Arc::new(Schema::new(vec![arrow_json_field]));
|
||||
|
||||
let rows: Vec<Option<&str>> = vec![None, Some(r#"{"a": 1}"#), Some(r#"{"b": 2}"#)];
|
||||
let string_array: Arc<dyn arrow_array::Array> = match input_type {
|
||||
DataType::Utf8 => Arc::new(arrow_array::StringArray::from(rows.clone())),
|
||||
DataType::LargeUtf8 => Arc::new(arrow_array::LargeStringArray::from(rows.clone())),
|
||||
other => panic!("unsupported arrow.json backing type for this test: {other:?}"),
|
||||
};
|
||||
let batch = RecordBatch::try_new(arrow_json_schema, vec![string_array]).unwrap();
|
||||
|
||||
// This must not fail with a schema-mismatch error.
|
||||
table.add(batch).execute().await.unwrap();
|
||||
|
||||
assert_eq!(table.count_rows(None).await.unwrap(), rows.len());
|
||||
|
||||
// A lance.json column is read back as Utf8 carrying arrow.json extension metadata.
|
||||
let results: Vec<RecordBatch> = table
|
||||
.query()
|
||||
.select(Select::columns(&["data"]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap()
|
||||
.try_collect()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(results.len(), 1);
|
||||
let batch = &results[0];
|
||||
assert_eq!(batch.num_rows(), rows.len());
|
||||
|
||||
let json_col = batch.column(0);
|
||||
assert_eq!(json_col.data_type(), &DataType::Utf8);
|
||||
let json_strs = json_col.as_string::<i32>();
|
||||
|
||||
for (i, expected) in rows.iter().enumerate() {
|
||||
match expected {
|
||||
None => assert!(json_strs.is_null(i), "row {i} expected null"),
|
||||
Some(raw) => {
|
||||
assert!(!json_strs.is_null(i), "row {i} expected non-null");
|
||||
let actual: serde_json::Value = serde_json::from_str(json_strs.value(i))
|
||||
.expect("read-back JSON should be valid");
|
||||
let expected: serde_json::Value =
|
||||
serde_json::from_str(raw).expect("expected JSON should be valid");
|
||||
assert_eq!(actual, expected, "row {i} JSON mismatch");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,6 +13,7 @@ use datafusion_physical_expr::expressions::{CastExpr, Literal};
|
||||
use datafusion_physical_plan::expressions::Column;
|
||||
use datafusion_physical_plan::projection::ProjectionExec;
|
||||
use datafusion_physical_plan::{ExecutionPlan, PhysicalExpr};
|
||||
use lance_arrow::json::{is_arrow_json_field, is_json_field};
|
||||
|
||||
use crate::{Error, Result};
|
||||
|
||||
@@ -64,6 +65,18 @@ fn build_field_exprs(
|
||||
let input_field = &input_fields[input_idx];
|
||||
let input_expr = get_input_expr(input_idx);
|
||||
|
||||
// Special case: input is arrow.json (PyArrow pa.json_() extension type backed by
|
||||
// Utf8/LargeUtf8) and the table field is lance.json (backed by LargeBinary).
|
||||
// Lance-core's write path already handles the arrow.json → lance.json conversion
|
||||
// (including JSONB encoding), so we pass the expression through unchanged and let
|
||||
// lance-core deal with it. Attempting to cast Utf8 → LargeBinary here would
|
||||
// produce a field whose metadata still identifies it as arrow.json, which then
|
||||
// causes a schema-mismatch error inside lance-core.
|
||||
if is_arrow_json_field(input_field) && is_json_field(table_field) {
|
||||
result.push((input_expr, Arc::clone(input_field) as FieldRef));
|
||||
continue;
|
||||
}
|
||||
|
||||
let expr = match (input_field.data_type(), table_field.data_type()) {
|
||||
// Both are structs: recurse into sub-fields to handle subschemas and casts.
|
||||
(DataType::Struct(in_children), DataType::Struct(tbl_children))
|
||||
@@ -618,4 +631,75 @@ mod tests {
|
||||
.unwrap();
|
||||
assert_eq!(a.values(), &[1, 3]);
|
||||
}
|
||||
|
||||
/// `arrow.json` input (PyArrow `pa.json_()`, Utf8/LargeUtf8 + extension metadata) against a
|
||||
/// `lance.json` table field (LargeBinary + extension metadata) must be passed through
|
||||
/// without a cast so that lance-core can perform its own arrow.json → JSONB conversion.
|
||||
///
|
||||
/// Before the fix, `cast_to_table_schema` attempted a `Utf8 → LargeBinary` DataFusion
|
||||
/// cast that preserved the wrong extension metadata, causing lance-core to reject the
|
||||
/// batch with a "json vs large_binary" schema-mismatch error.
|
||||
#[rstest::rstest]
|
||||
#[case::utf8(DataType::Utf8)]
|
||||
#[case::large_utf8(DataType::LargeUtf8)]
|
||||
#[tokio::test]
|
||||
async fn test_arrow_json_passthrough_to_lance_json(#[case] input_type: DataType) {
|
||||
use lance_arrow::ARROW_EXT_NAME_KEY;
|
||||
use lance_arrow::json::{ARROW_JSON_EXT_NAME, json_field};
|
||||
|
||||
// Build a table schema with a lance.json field (LargeBinary + lance.json metadata).
|
||||
let lance_field = json_field("data", true);
|
||||
let table_schema = Schema::new(vec![lance_field]);
|
||||
|
||||
// Build an input batch with an arrow.json field (Utf8/LargeUtf8 + arrow.json metadata).
|
||||
let arrow_meta = std::collections::HashMap::from([(
|
||||
ARROW_EXT_NAME_KEY.to_string(),
|
||||
ARROW_JSON_EXT_NAME.to_string(),
|
||||
)]);
|
||||
let arrow_field = Field::new("data", input_type.clone(), true).with_metadata(arrow_meta);
|
||||
let input_schema = Arc::new(Schema::new(vec![arrow_field]));
|
||||
|
||||
let values = vec![Some(r#"{"x": 1}"#), None, Some(r#"{"y": 2}"#)];
|
||||
let input_array: Arc<dyn arrow_array::Array> = match input_type {
|
||||
DataType::Utf8 => Arc::new(StringArray::from(values)),
|
||||
DataType::LargeUtf8 => Arc::new(arrow_array::LargeStringArray::from(values)),
|
||||
other => panic!("unsupported arrow.json backing type for this test: {other:?}"),
|
||||
};
|
||||
let input_batch = RecordBatch::try_new(input_schema, vec![input_array]).unwrap();
|
||||
|
||||
let plan = plan_from_batch(input_batch).await;
|
||||
let projected = cast_to_table_schema(plan, &table_schema).unwrap();
|
||||
|
||||
// The projected schema's "data" field must carry arrow.json metadata
|
||||
// (the input field), not be silently dropped or miscast.
|
||||
let out_field = projected.schema().field_with_name("data").unwrap().clone();
|
||||
assert_eq!(out_field.data_type(), &input_type);
|
||||
assert_eq!(
|
||||
out_field
|
||||
.metadata()
|
||||
.get(ARROW_EXT_NAME_KEY)
|
||||
.map(|s| s.as_str()),
|
||||
Some(ARROW_JSON_EXT_NAME),
|
||||
"output field must still carry arrow.json metadata so lance-core can handle it"
|
||||
);
|
||||
|
||||
// The data must flow through correctly (3 rows, no panic).
|
||||
let result = collect(projected).await;
|
||||
assert_eq!(result.num_rows(), 3);
|
||||
let (v0, v2) = match input_type {
|
||||
DataType::Utf8 => {
|
||||
let col: &StringArray = result.column(0).as_any().downcast_ref().unwrap();
|
||||
(col.value(0).to_string(), col.value(2).to_string())
|
||||
}
|
||||
DataType::LargeUtf8 => {
|
||||
let col: &arrow_array::LargeStringArray =
|
||||
result.column(0).as_any().downcast_ref().unwrap();
|
||||
(col.value(0).to_string(), col.value(2).to_string())
|
||||
}
|
||||
_ => unreachable!(),
|
||||
};
|
||||
assert_eq!(v0, r#"{"x": 1}"#);
|
||||
assert!(result.column(0).is_null(1));
|
||||
assert_eq!(v2, r#"{"y": 2}"#);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user